diff mbox

[v3] poly1305: generic C can be faster on chips with slow unaligned access

Message ID 20161107194345.19955-1-Jason@zx2c4.com (mailing list archive)
State Superseded
Delegated to: Herbert Xu
Headers show

Commit Message

Jason A. Donenfeld Nov. 7, 2016, 7:43 p.m. UTC 
By using the unaligned access helpers, we drastically improve
performance on small MIPS routers that have to go through the exception
fix-up handler for these unaligned accesses.

Signed-off-by: Jason A. Donenfeld <Jason@zx2c4.com>
---
 crypto/poly1305_generic.c | 33 ++++++++++++++-------------------
 1 file changed, 14 insertions(+), 19 deletions(-)

Comments

kernel test robot Nov. 12, 2016, 11:27 p.m. UTC | #1 
Hi Jason,

[auto build test ERROR on cryptodev/master]
[also build test ERROR on v4.9-rc4 next-20161111]
[if your patch is applied to the wrong git tree, please drop us a note to help improve the system]

url:    https://github.com/0day-ci/linux/commits/Jason-A-Donenfeld/poly1305-generic-C-can-be-faster-on-chips-with-slow-unaligned-access/20161108-053912
base:   https://git.kernel.org/pub/scm/linux/kernel/git/herbert/cryptodev-2.6.git master
config: openrisc-allmodconfig (attached as .config)
compiler: or32-linux-gcc (GCC) 4.5.1-or32-1.0rc1
reproduce:
        wget https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/plain/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # save the attached .config to linux build tree
        make.cross ARCH=openrisc 

All errors (new ones prefixed by >>):

   crypto/poly1305_generic.c: In function 'poly1305_setrkey':
>> crypto/poly1305_generic.c:63:2: error: implicit declaration of function 'get_unaligned_le32'

vim +/get_unaligned_le32 +63 crypto/poly1305_generic.c

    57	}
    58	EXPORT_SYMBOL_GPL(crypto_poly1305_setkey);
    59	
    60	static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key)
    61	{
    62		/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
  > 63		dctx->r[0] = (get_unaligned_le32(key +  0) >> 0) & 0x3ffffff;
    64		dctx->r[1] = (get_unaligned_le32(key +  3) >> 2) & 0x3ffff03;
    65		dctx->r[2] = (get_unaligned_le32(key +  6) >> 4) & 0x3ffc0ff;
    66		dctx->r[3] = (get_unaligned_le32(key +  9) >> 6) & 0x3f03fff;

---
0-DAY kernel test infrastructure                Open Source Technology Center
https://lists.01.org/pipermail/kbuild-all                   Intel Corporation
diff mbox

Patch

diff --git a/crypto/poly1305_generic.c b/crypto/poly1305_generic.c
index 2df9835d..7a77cfc 100644
--- a/crypto/poly1305_generic.c
+++ b/crypto/poly1305_generic.c
@@ -33,11 +33,6 @@  static inline u32 and(u32 v, u32 mask)
 	return v & mask;
 }
 
-static inline u32 le32_to_cpuvp(const void *p)
-{
-	return le32_to_cpup(p);
-}
-
 int crypto_poly1305_init(struct shash_desc *desc)
 {
 	struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
@@ -65,19 +60,19 @@  EXPORT_SYMBOL_GPL(crypto_poly1305_setkey);
 static void poly1305_setrkey(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
 	/* r &= 0xffffffc0ffffffc0ffffffc0fffffff */
-	dctx->r[0] = (le32_to_cpuvp(key +  0) >> 0) & 0x3ffffff;
-	dctx->r[1] = (le32_to_cpuvp(key +  3) >> 2) & 0x3ffff03;
-	dctx->r[2] = (le32_to_cpuvp(key +  6) >> 4) & 0x3ffc0ff;
-	dctx->r[3] = (le32_to_cpuvp(key +  9) >> 6) & 0x3f03fff;
-	dctx->r[4] = (le32_to_cpuvp(key + 12) >> 8) & 0x00fffff;
+	dctx->r[0] = (get_unaligned_le32(key +  0) >> 0) & 0x3ffffff;
+	dctx->r[1] = (get_unaligned_le32(key +  3) >> 2) & 0x3ffff03;
+	dctx->r[2] = (get_unaligned_le32(key +  6) >> 4) & 0x3ffc0ff;
+	dctx->r[3] = (get_unaligned_le32(key +  9) >> 6) & 0x3f03fff;
+	dctx->r[4] = (get_unaligned_le32(key + 12) >> 8) & 0x00fffff;
 }
 
 static void poly1305_setskey(struct poly1305_desc_ctx *dctx, const u8 *key)
 {
-	dctx->s[0] = le32_to_cpuvp(key +  0);
-	dctx->s[1] = le32_to_cpuvp(key +  4);
-	dctx->s[2] = le32_to_cpuvp(key +  8);
-	dctx->s[3] = le32_to_cpuvp(key + 12);
+	dctx->s[0] = get_unaligned_le32(key +  0);
+	dctx->s[1] = get_unaligned_le32(key +  4);
+	dctx->s[2] = get_unaligned_le32(key +  8);
+	dctx->s[3] = get_unaligned_le32(key + 12);
 }
 
 unsigned int crypto_poly1305_setdesckey(struct poly1305_desc_ctx *dctx,
@@ -137,11 +132,11 @@  static unsigned int poly1305_blocks(struct poly1305_desc_ctx *dctx,
 	while (likely(srclen >= POLY1305_BLOCK_SIZE)) {
 
 		/* h += m[i] */
-		h0 += (le32_to_cpuvp(src +  0) >> 0) & 0x3ffffff;
-		h1 += (le32_to_cpuvp(src +  3) >> 2) & 0x3ffffff;
-		h2 += (le32_to_cpuvp(src +  6) >> 4) & 0x3ffffff;
-		h3 += (le32_to_cpuvp(src +  9) >> 6) & 0x3ffffff;
-		h4 += (le32_to_cpuvp(src + 12) >> 8) | hibit;
+		h0 += (get_unaligned_le32(src +  0) >> 0) & 0x3ffffff;
+		h1 += (get_unaligned_le32(src +  3) >> 2) & 0x3ffffff;
+		h2 += (get_unaligned_le32(src +  6) >> 4) & 0x3ffffff;
+		h3 += (get_unaligned_le32(src +  9) >> 6) & 0x3ffffff;
+		h4 += (get_unaligned_le32(src + 12) >> 8) | hibit;
 
 		/* h *= r */
 		d0 = mlt(h0, r0) + mlt(h1, s4) + mlt(h2, s3) +